© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44889
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paradox
    -0.08
     één
    -0.08
     contrast
    -0.08
     ess
    -0.08
     കുറ
    -0.08
    ":
    -0.07
    Providing
    -0.07
     parado
    -0.07
    ഴ്
    -0.07
    YOUR
    -0.07
    POSITIVE LOGITS
     nope
    0.09
    -aaral
    0.08
     లేదు
    0.08
     kaore
    0.08
    ATES
    0.08
    akhstan
    0.08
     முடிய
    0.08
     divisible
    0.08
    由于
    0.08
     فرد
    0.08
    Activations Density 0.024%

    No Known Activations